Fine-tuned on eco-products domain (brand, product name, origin)

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: cc-by-4.0
+base_model: bltlab/queryner-bert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: checkpoints
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# checkpoints
+
+This model is a fine-tuned version of [bltlab/queryner-bert-base-uncased](https://huggingface.co/bltlab/queryner-bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1054
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9302        | 1.0   | 797  | 0.1401          |
+| 0.163         | 2.0   | 1594 | 0.1058          |
+| 0.1035        | 3.0   | 2391 | 0.1054          |
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.9.0
+- Datasets 3.2.0
+- Tokenizers 0.22.2

best/config.json

@@ -0,0 +1,99 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-UoM",
+    "1": "B-color",
+    "2": "B-condition",
+    "3": "B-content",
+    "4": "B-core_product_type",
+    "5": "B-creator",
+    "6": "B-department",
+    "7": "B-material",
+    "8": "B-modifier",
+    "9": "B-occasion",
+    "10": "B-origin",
+    "11": "B-price",
+    "12": "B-product_name",
+    "13": "B-product_number",
+    "14": "B-quantity",
+    "15": "B-shape",
+    "16": "B-time",
+    "17": "I-UoM",
+    "18": "I-color",
+    "19": "I-condition",
+    "20": "I-content",
+    "21": "I-core_product_type",
+    "22": "I-creator",
+    "23": "I-department",
+    "24": "I-material",
+    "25": "I-modifier",
+    "26": "I-occasion",
+    "27": "I-origin",
+    "28": "I-price",
+    "29": "I-product_name",
+    "30": "I-product_number",
+    "31": "I-quantity",
+    "32": "I-shape",
+    "33": "I-time",
+    "34": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-UoM": 0,
+    "B-color": 1,
+    "B-condition": 2,
+    "B-content": 3,
+    "B-core_product_type": 4,
+    "B-creator": 5,
+    "B-department": 6,
+    "B-material": 7,
+    "B-modifier": 8,
+    "B-occasion": 9,
+    "B-origin": 10,
+    "B-price": 11,
+    "B-product_name": 12,
+    "B-product_number": 13,
+    "B-quantity": 14,
+    "B-shape": 15,
+    "B-time": 16,
+    "I-UoM": 17,
+    "I-color": 18,
+    "I-condition": 19,
+    "I-content": 20,
+    "I-core_product_type": 21,
+    "I-creator": 22,
+    "I-department": 23,
+    "I-material": 24,
+    "I-modifier": 25,
+    "I-occasion": 26,
+    "I-origin": 27,
+    "I-price": 28,
+    "I-product_name": 29,
+    "I-product_number": 30,
+    "I-quantity": 31,
+    "I-shape": 32,
+    "I-time": 33,
+    "O": 34
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478b01f78433afe51b7996a665f7dfcf3485bc8b7dc2e81490b68ba3a8b83fe1
+size 435697596

best/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

best/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ccb79f1086db38d7d577f3d45e4c4374a22545678b4ecce3c2cd7c2111359f
+size 5969

config.json

@@ -0,0 +1,99 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-UoM",
+    "1": "B-color",
+    "2": "B-condition",
+    "3": "B-content",
+    "4": "B-core_product_type",
+    "5": "B-creator",
+    "6": "B-department",
+    "7": "B-material",
+    "8": "B-modifier",
+    "9": "B-occasion",
+    "10": "B-origin",
+    "11": "B-price",
+    "12": "B-product_name",
+    "13": "B-product_number",
+    "14": "B-quantity",
+    "15": "B-shape",
+    "16": "B-time",
+    "17": "I-UoM",
+    "18": "I-color",
+    "19": "I-condition",
+    "20": "I-content",
+    "21": "I-core_product_type",
+    "22": "I-creator",
+    "23": "I-department",
+    "24": "I-material",
+    "25": "I-modifier",
+    "26": "I-occasion",
+    "27": "I-origin",
+    "28": "I-price",
+    "29": "I-product_name",
+    "30": "I-product_number",
+    "31": "I-quantity",
+    "32": "I-shape",
+    "33": "I-time",
+    "34": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-UoM": 0,
+    "B-color": 1,
+    "B-condition": 2,
+    "B-content": 3,
+    "B-core_product_type": 4,
+    "B-creator": 5,
+    "B-department": 6,
+    "B-material": 7,
+    "B-modifier": 8,
+    "B-occasion": 9,
+    "B-origin": 10,
+    "B-price": 11,
+    "B-product_name": 12,
+    "B-product_number": 13,
+    "B-quantity": 14,
+    "B-shape": 15,
+    "B-time": 16,
+    "I-UoM": 17,
+    "I-color": 18,
+    "I-condition": 19,
+    "I-content": 20,
+    "I-core_product_type": 21,
+    "I-creator": 22,
+    "I-department": 23,
+    "I-material": 24,
+    "I-modifier": 25,
+    "I-occasion": 26,
+    "I-origin": 27,
+    "I-price": 28,
+    "I-product_name": 29,
+    "I-product_number": 30,
+    "I-quantity": 31,
+    "I-shape": 32,
+    "I-time": 33,
+    "O": 34
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478b01f78433afe51b7996a665f7dfcf3485bc8b7dc2e81490b68ba3a8b83fe1
+size 435697596

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ccb79f1086db38d7d577f3d45e4c4374a22545678b4ecce3c2cd7c2111359f
+size 5969